Sciweavers

697 search results - page 18 / 140
» Strategies to Parallelize ILP Systems
Sort
View
IPPS
2006
IEEE
14 years 2 months ago
Online strategies for high-performance power-aware thread execution on emerging multiprocessors
Granularity control is an effective means for trading power consumption with performance on dense shared memory multiprocessors, such as multi-SMT and multi-CMP systems. In this p...
Matthew Curtis-Maury, James Dzierwa, Christos D. A...
CASCON
1996
101views Education» more  CASCON 1996»
13 years 9 months ago
Design patterns in enterprise
The Enterprise parallel programming system allows programmers to create, compile, execute, and debug parallel applications that execute over a network of workstations. The run-tim...
Steve MacDonald
ARTDB
1997
Springer
269views Database» more  ARTDB 1997»
14 years 19 days ago
Parallel Event Detection in Active Database Systems: The Heart of the Matter
This paper proposes a strategy for parallel composite event detection in Active database systems (DBS). Up to now, the detection is sequential and totally synchronized, and thus p...
Ulrike Jaeger, Johann K. Obermaier
ICS
2004
Tsinghua U.
14 years 1 months ago
Scaling the issue window with look-ahead latency prediction
In contemporary out-of-order superscalar design, high IPC is mainly achieved by exposing high instruction level parallelism (ILP). Scaling issue window size can certainly provide ...
Yongxiang Liu, Anahita Shayesteh, Gokhan Memik, Gl...
CASES
2003
ACM
14 years 3 days ago
Efficient spill code for SDRAM
Processors such as StrongARM and memory such as SDRAM enable efficient execution of multiple loads and stores in a single instruction. This is particularly useful in connection wi...
V. Krishna Nandivada, Jens Palsberg